INDEX

Explanations

mentions of "The New York Times" or promotions from the newspaper

oai_token-act-pair · gpt-3.5-turbo

references to "The New York Times."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

razil

-0.83

ressive

-0.80

ardless

-0.79

reating

-0.78

atical

-0.77

rd

-0.77

cius

-0.76

sed

-0.75

itionally

-0.74

resent

-0.74

POSITIVE LOGITS

 Magazine

0.99

 bestselling

0.95

 Dispatch

0.88

 Literary

0.88

 Publishing

0.85

 Square

0.83

 Newsp

0.80

 Editorial

0.80

 Editors

0.77

 Herald

0.77

Activations Density 0.017%

mentions of "The New York Times" or promotions from the newspaper

references to "The New York Times."

No Comments

No Known Activations